© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47564
    Prev
    Next
    INDEX
    Explanations

    conference and standards proceedings

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects domain-specific capitalized terms and proper names (e.g. conference titles, technical field names, acronyms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     currently
    -0.96
     weekly
    -0.95
    乃是
    -0.92
    },[])
    -0.91
     manually
    -0.91
     monthly
    -0.91
     visitors
    -0.90
     precious
    -0.90
     readers
    -0.90
     someday
    -0.90
    POSITIVE LOGITS
    因為
    1.04
    ichtlich
    0.92
     segala
    0.90
    ใคร
    0.86
    >';
    0.86
    ]',
    0.85
     référence
    0.85
    🩺
    0.84
    etsch
    0.84
     october
    0.83
    Activations Density 0.015%

    No Known Activations